Enhanced Clarification Prompts for Ambiguous Voice Commands
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated assistants often struggle with ambiguous user commands, leading to prolonged interactions, errant inputs, and user frustration due to the limitations of natural language-only clarification prompts, which can result in incorrect disambiguation and abandonment of intended goals.
Innovation Solution
Implementing an enhanced clarification prompt that includes additional audio or visual content, such as musical snippets or images, to assist users in differentiating between candidate responsive actions, selectively provided based on conditions like historical interaction data, semantic similarity, and inverse document frequency, to reduce interaction duration and improve disambiguation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If natural language-only clarification prompts are used, then the system maintains simplicity in prompt structure, but user interaction time increases and disambiguation accuracy decreases
Solution Approach 1:
The patent transitions from one-dimensional text-based clarification prompts to multi-dimensional prompts that incorporate audio snippets, images, and text. This dimensional expansion allows users to disambiguate between candidate actions through multiple sensory channels simultaneously, reducing interaction time without increasing structural complexity
2Ease of manufacture
If natural language-only clarification prompts are used, then the system maintains ease of implementation, but disambiguation accuracy deteriorates
Solution Approach 1:
The patent segments the clarification prompt into distinct modular components: text descriptions, audio snippets, and images. Each component serves a specific disambiguation function and can be independently generated and selected based on the conversation context, maintaining implementation ease while improving accuracy
3Measurement precision
If enhanced clarification prompts with audio and visual content are provided, then disambiguation accuracy improves, but system complexity increases
Solution Approach 1:
The patent implements dynamic selection of clarification prompt types based on real-time analysis of conversation context, user preferences, and candidate action characteristics. The system adaptively determines whether to use text-only, audio-enhanced, image-enhanced, or full multi-modal prompts, optimizing disambiguation accuracy while managing system complexity through context-aware adaptation
4Productivity
If enhanced clarification prompts are selectively provided based on conditions, then interaction efficiency improves, but processing requirements increase
Solution Approach 1:
The patent performs preliminary analysis of the conversation context, user profile, and candidate actions before generating clarification prompts. This advance preparation allows the system to pre-determine the appropriate prompt type and pre-fetch necessary audio or image resources, improving interaction efficiency while managing processing resources through proactive preparation
Data Source
AI summary
Implementations described herein receive audio data that captures a spoken utterance, generate, based on processing the audio data, a recognition that corresponds to the spoken utterance, and determine, based on processing the recognition, that the spoken utterance is ambiguous (i.e., is interpretable as requesting performance of a first particular action exclusively and is also interpretable a second particular action exclusively). In response to determining that the spoken utterance is ambiguous, implementations determine to provide an enhanced clarification prompt that renders output that is in addition to natural language. The enhanced clarification prompt solicits further user interface input for disambiguating between the first particular action and the second particular action. Determining to provide the enhanced clarification prompt includes a current or prior determination to provide the enhanced clarification prompt instead of a natural language (NL) only clarification prompt that is restricted to rendering natural language.